Search Results for "light weight linux" - Page 95
Sort By:
Showing 2374 open source projects for "light weight linux"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
LocalLLM Studio
Chat with local GGUF LLMs on your own machine
Chat with local GGUF LLMs on your own machine — private, offline, model-agnostic. LLM Apps & Agents Apache-2.0 v1.0.5 100% AI-built 0 0 Get LocalLLM Studio View source Website Run open-weight language models (GGUF) fully offline on your own hardware via llama.cpp: a chat interface with system prompts, conversation history, adjustable sampling, and simple retrieval over your own files. You supply the model file — nothing is sent to any server. At a glance Downloads 0 Views 5 Rating No... -
2
Hy4 preview
770B MoE model for coding, research, reasoning, and long-context work
Hy4 preview is Tencent’s open-weight flagship Mixture-of-Experts language model designed for advanced reasoning, software engineering, productivity, scientific research, and long-horizon tasks. It contains 770B backbone parameters while activating 49B per token across 78 layers, with 256 routed experts and one shared expert in each MoE layer. Its architecture uses Gated DeepSeek Sparse Attention with IndexCache for cross-layer sparse-index reuse and identity Hyper-Connections to improve... -
3
Qwen3.8-Flash-Next
Efficient multimodal MoE model for coding, reasoning, and AI agents
Qwen3.8-Flash-Next is Qwen’s experimental open-weight multimodal model previewing the architecture planned for Qwen4. It uses 125B language-model parameters with only 6B activated per token, supplemented by 51B n-gram embedding parameters and 4B for multi-token prediction. Its hybrid architecture combines Gated DeltaNet with Qwen Sparse Attention (QSA), which processes micro-blocks rather than individual tokens to reduce latency in long-context agent workloads. The model also introduces... -
4
Solar Open 2
Efficient 250B MoE model for agents, coding, and long-context work
Solar Open 2 is Upstage’s 250B-A15B open-weight large language model designed for agentic workflows, office productivity, document-intensive tasks, coding, and reasoning. Its Hybrid-Attention Mixture-of-Experts architecture contains 250B total parameters while activating only 15B per token, combining three linear-attention layers with one softmax-attention layer for efficient inference. The model supports a native 1M-token context window and uses NoPE instead of rotary positional encoding,... -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
Qwen3.8-27B
Dense 27B multimodal model for coding, agents, and visual reasoning
Qwen3.8-27B is a compact, open-weight dense multimodal model designed for advanced coding, professional work, research, visual understanding, and long-horizon agentic tasks. Built on the Qwen3.5 architecture, it contains 27B parameters and combines Gated DeltaNet with gated attention across 64 layers. The model natively understands text, images, and videos, including documents, STEM diagrams, and hour-scale video content. Agent capabilities emphasize autonomous planning, environment... -
6
Qwen3.8-2.4T-A95B
Massive 2.4T MoE model for coding, agents, research, and reasoning
Qwen3.8-2.4T-A95B is Qwen’s largest open-weight model and the first Qwen-Max-class model released openly, targeting advanced coding, professional work, research, and long-horizon agentic tasks. It uses a massive Mixture-of-Experts architecture with 2.4 trillion total parameters while activating 95B per token, combining Gated DeltaNet and attention layers across 512 experts. The model emphasizes reliable autonomous execution, including stronger planning, environment feedback handling, and... -
7
Muse Glimmer
Local multimodal 30B model for autonomous agents, coding, and tools
Muse Glimmer-30B is Meta Superintelligence Lab’s open-weight multimodal model built specifically for autonomous agentic tasks on consumer hardware. Distilled from the larger Muse Spark, it combines multi-step reasoning, reliable tool use, coding, failure recovery, and image understanding in a dense 29.6B-parameter architecture with a dedicated 1.8B-parameter perception encoder. It supports more than 100 languages and a 131K+ token context window, allowing agents to maintain coherent plans... -
8
Inkling-Small
Efficient multimodal MoE model for coding, tools, and reasoning
Inkling-Small is an open-weight general-purpose multimodal model from Thinking Machines Lab, designed for agentic systems, coding assistants, chatbots, retrieval workflows, and natural-language applications. It accepts text, images, and audio as input and produces text output, with multilingual and multi-programming-language capabilities. The model uses a sparse Mixture-of-Experts architecture with 276B total parameters and 12B active per token, enabling strong performance with lower... -
9
Gemma 4 12B
Unified multimodal Gemma model for local coding and reasoning
Gemma 4 12B is Google DeepMind’s unified open-weight multimodal model designed for efficient local reasoning, coding, and multimodal understanding. Unlike other Gemma 4 models that rely on separate encoders, the 12B Unified model uses an encoder-free architecture that projects raw image patches and audio waveforms directly into the language model’s embedding space, reducing multimodal latency and simplifying fine-tuning. It supports text, image, audio, and video inputs with text output,... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
Gemma 4
Google’s flagship dense multimodal model for coding and reasoning
Gemma 4 is Google DeepMind’s flagship dense open-weight multimodal model, designed for high-end reasoning, coding, agentic workflows, and multimodal understanding. The model contains approximately 30.7B parameters and supports text and image inputs with text generation output, while also processing video as image-frame sequences. Built as the most capable model in the Gemma 4 family, it combines strong reasoning performance with a large 256K-token context window and configurable thinking... -
11
Command A+
4-bit Command A+ model for enterprise agents and multilingual tasks
Command A+ 05-2026 W4A4 is a 4-bit quantized version of Cohere’s open-source Command A+ model, optimized for enterprise-grade agentic, multilingual, and reasoning-heavy workloads. It supports text and image inputs, generates text outputs, and uses a sparse Mixture-of-Experts Transformer architecture with 218B total parameters and 25B active parameters. The W4A4 release applies 4-bit weight and activation quantization mainly to MoE experts, preserving attention components at full precision to... -
12
Qwen3.6-35B-A3B-FP8
FP8 Qwen model for efficient multimodal coding and agent tasks
Qwen3.6-35B-A3B-FP8 is an FP8-quantized version of Qwen3.6 designed to deliver nearly the same performance as the original model while improving deployment efficiency. It is a multimodal open-weight model that combines a causal language model with a vision encoder, supporting text, image, and video inputs. Built for stability and real-world developer use, it emphasizes agentic coding, repository-level reasoning, and productive long-context workflows. A key capability is thinking... -
13
Qwen3-Next
Qwen3-Next: 80B instruct LLM with ultra-long context up to 1M tokens
Qwen3-Next-80B-A3B-Instruct is the flagship release in the Qwen3-Next series, designed as a next-generation foundation model for ultra-long context and efficient reasoning. With 80B total parameters and 3B activated at a time, it leverages hybrid attention (Gated DeltaNet + Gated Attention) and a high-sparsity Mixture-of-Experts architecture to achieve exceptional efficiency. The model natively supports a context length of 262K tokens and can be extended up to 1 million tokens using RoPE... -
14
Oshin OS
Arch based OS for mitigating cyber bullying and cyber threats
Welcome to Oshin OS Oshin OS is an Ezarch Linux-based free, safe, and open-source operating system for your kids and yourself that allows you to stay safe in the world of technology without compromising on your daily requirements. Oshin OS will ensure your safety, comfort, accessibility, and exploration opportunities. We offer a secure operating system for everyone in this digital world. Live boot Username: oshin Live boot Password: oshin The source code is hosted on Github:... -
15
Mergist
Mergist is an online tool to combine multiple PDF files into one
Mergist is an online tool to combine multiple PDF files into one. Mergist has no ads, no file size limits, and your files never leave your device. -
16
WordPress
The Official WordPress Project on SourceForge.
This is the official WordPress Project on SourceForge, which means it will be regularly updated whenever WordPress releases a new version of their CMS. About WordPress: WordPress is publishing software with a focus on ease of use, speed and a great user experience. WordPress is blessed with an active community, which is the heart of open source software. WordPress is a powerful semantic publishing platform, and it comes with a great set of features designed to make your experience... -
17
Coypu is an abstract layer, graphic widgets implementation. It is written in C and is highly portable to most architectures and software/hardware backends (X11, Directfb, GLUT, SDL, WIN32). Being fast and light, it's mainly targeted at embedded devices.
-
18
Smaug Flash
304B MoE model optimized for agentic coding and long-running workflows
Smaug Flash is an open-weight agentic coding model from Abacus.AI, fine-tuned from DeepSeek-V4-Flash-0731 to improve autonomous software engineering, tool use, and long-running agent workflows. It uses a 304B-parameter Mixture-of-Experts architecture with 43 layers, 256 routed experts, six selected experts per token, and one shared expert. Its attention system combines Multi-Head Latent Attention with a sparse token indexer, while DSpark multi-token prediction provides speculative decoding... -
19
Qwable-v1
Agentic coding model combining Opus reasoning and Fable tools
Qwable-v1 is an open-weight agentic coding model created through a chained distillation process based on Qwen3.6-35B-A3B. The model combines two distinct training stages: first, it was fine-tuned on reasoning traces derived from Claude Opus 4.7 to improve structured reasoning, and then further trained on Claude Fable-5 agentic tool-use traces to develop autonomous coding and tool-calling behavior. The result is a 35B Mixture-of-Experts model with only 3B active parameters that can switch... -
20
Mistral Large 3 675B Base 2512
Frontier-scale 675B multimodal base model for custom AI training
Mistral Large 3 675B Base 2512 is the foundational, pre-trained version of the Mistral Large 3 family, built as a frontier-scale multimodal Mixture-of-Experts model with 41B active parameters and a total size of 675B. It is trained from scratch using 3000 H200 GPUs, making it one of the most advanced and compute-intensive open-weight models available. As the base version, it is not fine-tuned for instruction following or reasoning, making it ideal for teams planning their own domain-specific... -
21
VedAstro
A non-profit, open source for Vedic Astrology with free and Open API
Match is a calculator for checking marriage or friendship compatibility. Muhurtha is used for finding good timing and using the Life Predictor you can make predictions up to 120 years. Explore each calculator to get a deep understanding of Vedic Astrology. Anybody who has studied Vedic Astrology knows well how accurate it can be. But also how complex it can get to make accurate predictions. It takes decades of experience to be able make accurate prediction. As such this knowledge only... -
22
Awesome Flickr Gallery
A WordPress plugin to create galleries using photos stored on Flickr
- Fast and light - uses intelligent caching to load galleries instantly - Support for both Public and Private photos - Create multiple galleries with different parameters - Select Photos from your Flickr Photostream, a Photoset, a Gallery, a Group or a set of tags - Multiple sorting options available so that you don't have to rely on Flickr's sorting options - Customizable image sizes with cropping settings - Infinitely customizable with custom CSS field - Fits into a sidebar widget... -
23
im-browser
MIB is a high-performance software package for image segmentation
Microscopy Image Browser (MIB) is a high-performance software package for advanced image processing, segmentation and visualization of multi-dimensional (2D-4D) light and electron microscopy datasets. Home page: http://mib.helsinki.fi -
24
zen-moment
Minimalist meditation timer with breathing exercises and analytics
Zen Moment is a minimalist meditation and breathing practice tool designed to make mindfulness accessible to everyone. Built with modern web technologies and optimized for performance across all devices, this application provides a clean, distraction-free environment for meditation practice. Key features include a precise meditation timer supporting 1-999 minute sessions with multiple presets, guided 4-7-8 breathing exercises based on Dr. Weil's proven relaxation technique, and an...
